© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15114
    Prev
    Next
    INDEX
    Explanations

    CSS declarations

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    旆
    -15.88
    eree
    -15.81
     repay
    -15.56
    Criterion
    -15.56
     “…
    -15.50
     Trial
    -15.38
    Trial
    -15.25
    hek
    -15.13
     provid
    -14.94
    aris
    -14.94
    POSITIVE LOGITS
    /auto
    16.88
     }</
    15.50
    夹
    14.25
    igth
    14.19
    滚动
    13.88
    d
    13.25
     illeg
    12.69
    死了
    12.56
    拥
    12.56
    aling
    12.56
    Activations Density 0.095%

    No Known Activations